Michael A. Hedderich
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Michael A. Hedderich has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Dietrich Klakow
Saarland University
9 shared publications - Dawei Zhu
Saarland University Yupei Utrecht University Saarland University Saarland University Saarland University
4 shared publications - Andrew Yates
Johns Hopkins University, Baltimore, Maryland, USA
2 shared publications - Gerard de Melo
Hasso Plattner Institute, Potsdam, Germany and University of Potsdam, Potsdam, Germany
2 shared publications - Xiaoyu Shen
Saarland University Saarland Informatics Campus Germany
2 shared publications - Anna Khokhlova
Department of Language Science and Technology Saarland Informatics Campus Spoken Language Systems (LSV) Saarland University Germany
1 shared publication
Latest Publications
- Open Access
Meta Self-Refinement for Robust Learning with Weak Supervision
Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from weak supervision can be noisy, and the high capacity of DNNs enables them to easily overfit the label noise, resulting in poor generalization. Recent methods leverage self-training to build noise-resistant models, in which a teacher trained under weak supervision is used to provide highly confident labels for teaching the students. Nevertheless, the teacher derived from such frameworks may have fitted a substantial amount of noise and therefore produce incorrect pseudo-labels with high confidence, leading to severe error propagation. In this work, we propose Meta Self-Refinement (MSR), a noise-resistant learning framework, to effectively combat label noise from weak supervision. Instead of relying on a fixed teacher trained with noisy labels, we encourage the teacher to refine its pseudo-labels. At each training step, MSR performs a meta gradient descent on the current mini-batch to maximize the student performance on a clean validation set. Extensive experimentation on eight NLP benchmarks demonstrates that MSR is robust against label noise in all settings and outperforms state-of-the-art methods by up to 11.4% in accuracy and 9.26% in F1 score.
Open AccessMeta Self-Refinement for Robust Learning with Weak Supervision
Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from weak supervision can be noisy, and the high capacity of DNNs enables them to easily overfit the label noise, resulting in poor generalization. Recent methods leverage self-training to build noise-resistant models, in which a teacher trained under weak supervision is used to provide highly confident labels for teaching the students. Nevertheless, the teacher derived from such frameworks may have fitted a substantial amount of noise and therefore produce incorrect pseudo-labels with high confidence, leading to severe error propagation. In this work, we propose Meta Self-Refinement (MSR), a noise-resistant learning framework, to effectively combat label noise from weak supervision. Instead of relying on a fixed teacher trained with noisy labels, we encourage the teacher to refine its pseudo-labels. At each training step, MSR performs a meta gradient descent on the current mini-batch to maximize the student performance on a clean validation set. Extensive experimentation on eight NLP benchmarks demonstrates that MSR is robust against label noise in all settings and outperforms state-of-the-art methods by up to 11.4% in accuracy and 9.26% in F1 score.
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1043-1058
Meta Self-Refinement for Robust Learning with Weak Supervision
Dawei Zhu, Xiaoyu Shen, Michael Hedderich, Dietrich Klakow. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 1043-1058
Open AccessMeta Self-Refinement for Robust Learning with Weak Supervision
Dawei Zhu, Xiaoyu Shen, Michael Hedderich, Dietrich Klakow. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.
- Open Access
Label-Descriptive Patterns and Their Application to Characterizing Classification Errors
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors, but also gives a way to act and improve the classifier. We propose to discover those feature-value combinations (i.e., patterns) that strongly correlate with correct resp. erroneous predictions to obtain a global and interpretable description for arbitrary classifiers. We show this is an instance of the more general label description problem, which we formulate in terms of the Minimum Description Length principle. To discover a good pattern set, we develop the efficient Premise algorithm. Through an extensive set of experiments we show it performs very well in practice on both synthetic and real-world data. Unlike existing solutions, it ably recovers ground truth patterns, even on highly imbalanced data over many features. Through two case studies on Visual Question Answering and Named Entity Recognition, we confirm that Premise gives clear and actionable insight into the systematic errors made by modern NLP classifiers.
Open AccessLabel-Descriptive Patterns and Their Application to Characterizing Classification Errors
State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors, but also gives a way to act and improve the classifier. We propose to discover those feature-value combinations (i.e., patterns) that strongly correlate with correct resp. erroneous predictions to obtain a global and interpretable description for arbitrary classifiers. We show this is an instance of the more general label description problem, which we formulate in terms of the Minimum Description Length principle. To discover a good pattern set, we develop the efficient Premise algorithm. Through an extensive set of experiments we show it performs very well in practice on both synthetic and real-world data. Unlike existing solutions, it ably recovers ground truth patterns, even on highly imbalanced data over many features. Through two case studies on Visual Question Answering and Named Entity Recognition, we confirm that Premise gives clear and actionable insight into the systematic errors made by modern NLP classifiers.
- Open Access
Analysing the Noise Model Error for Realistic Noisy Label Data
Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these noisy labels is noise modelling where the underlying noise process is modelled. In this work, we study the quality of these estimated noise models from the theoretical side by deriving the expected error of the noise model. Apart from evaluating the theoretical results on commonly used synthetic noise, we also publish NoisyNER, a new noisy label dataset from the NLP domain that was obtained through a realistic distant supervision technique. It provides seven sets of labels with differing noise patterns to evaluate different noise levels on the same instances. Parallel, clean labels are available making it possible to study scenarios where a small amount of gold-standard data can be leveraged. Our theoretical results and the corresponding experiments give insights into the factors that influence the noise model estimation like the noise distribution and the sampling technique.
Open AccessAnalysing the Noise Model Error for Realistic Noisy Label Data
Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these noisy labels is noise modelling where the underlying noise process is modelled. In this work, we study the quality of these estimated noise models from the theoretical side by deriving the expected error of the noise model. Apart from evaluating the theoretical results on commonly used synthetic noise, we also publish NoisyNER, a new noisy label dataset from the NLP domain that was obtained through a realistic distant supervision technique. It provides seven sets of labels with differing noise patterns to evaluate different noise levels on the same instances. Parallel, clean labels are available making it possible to study scenarios where a small amount of gold-standard data can be leveraged. Our theoretical results and the corresponding experiments give insights into the factors that influence the noise model estimation like the noise distribution and the sampling technique.
- Open Access
On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers
Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is, however, understood about how fine-tuning affects the representations of pre-trained models and thereby the linguistic knowledge they encode. This paper contributes towards closing this gap. We study three different pre-trained models: BERT, RoBERTa, and ALBERT, and investigate through sentence-level probing how fine-tuning affects their representations. We find that for some probing tasks fine-tuning leads to substantial changes in accuracy, possibly suggesting that fine-tuning introduces or even removes linguistic knowledge from a pre-trained model. These changes, however, vary greatly across different models, fine-tuning and probing tasks. Our analysis reveals that while fine-tuning indeed changes the representations of a pre-trained model and these changes are typically larger for higher layers, only in very few cases, fine-tuning has a positive effect on probing accuracy that is larger than just using the pre-trained model with a strong pooling method. Based on our findings, we argue that both positive and negative effects of fine-tuning on probing require a careful interpretation.
Open AccessOn the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers
Fine-tuning pre-trained contextualized embedding models has become an integral part of the NLP pipeline. At the same time, probing has emerged as a way to investigate the linguistic knowledge captured by pre-trained models. Very little is, however, understood about how fine-tuning affects the representations of pre-trained models and thereby the linguistic knowledge they encode. This paper contributes towards closing this gap. We study three different pre-trained models: BERT, RoBERTa, and ALBERT, and investigate through sentence-level probing how fine-tuning affects their representations. We find that for some probing tasks fine-tuning leads to substantial changes in accuracy, possibly suggesting that fine-tuning introduces or even removes linguistic knowledge from a pre-trained model. These changes, however, vary greatly across different models, fine-tuning and probing tasks. Our analysis reveals that while fine-tuning indeed changes the representations of a pre-trained model and these changes are typically larger for higher layers, only in very few cases, fine-tuning has a positive effect on probing accuracy that is larger than just using the pre-trained model with a strong pooling method. Based on our findings, we argue that both positive and negative effects of fine-tuning on probing require a careful interpretation.
- Open Access
Learning Functions to Study the Benefit of Multitask Learning
We study and quantify the generalization patterns of multitask learning (MTL) models for sequence labeling tasks. MTL models are trained to optimize a set of related tasks jointly. Although multitask learning has achieved improved performance in some problems, there are also tasks that lose performance when trained together. These mixed results motivate us to study the factors that impact the performance of MTL models. We note that theoretical bounds and convergence rates for MTL models exist, but they rely on strong assumptions such as task relatedness and the use of balanced datasets. To remedy these limitations, we propose the creation of a task simulator and the use of Symbolic Regression to learn expressions relating model performance to possible factors of influence. For MTL, we study the model performance against the number of tasks (T), the number of samples per task (n) and the task relatedness measured by the adjusted mutual information (AMI). In our experiments, we could empirically find formulas relating model performance with factors of sqrt(n), sqrt(T), which are equivalent to sound mathematical proofs in Maurer[2016], and we went beyond by discovering that performance relates to a factor of sqrt(AMI).
Open AccessLearning Functions to Study the Benefit of Multitask Learning
We study and quantify the generalization patterns of multitask learning (MTL) models for sequence labeling tasks. MTL models are trained to optimize a set of related tasks jointly. Although multitask learning has achieved improved performance in some problems, there are also tasks that lose performance when trained together. These mixed results motivate us to study the factors that impact the performance of MTL models. We note that theoretical bounds and convergence rates for MTL models exist, but they rely on strong assumptions such as task relatedness and the use of balanced datasets. To remedy these limitations, we propose the creation of a task simulator and the use of Symbolic Regression to learn expressions relating model performance to possible factors of influence. For MTL, we study the model performance against the number of tasks (T), the number of samples per task (n) and the task relatedness measured by the adjusted mutual information (AMI). In our experiments, we could empirically find formulas relating model performance with factors of sqrt(n), sqrt(T), which are equivalent to sound mathematical proofs in Maurer[2016], and we went beyond by discovering that performance relates to a factor of sqrt(AMI).
- Open Access
Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá
The lack of labeled training data has limited the development of natural language processing tools, such as named entity recognition, for many languages spoken in developing countries. Techniques such as distant and weak supervision can be used to create labeled data in a (semi-) automatic way. Additionally, to alleviate some of the negative effects of the errors in automatic annotation, noise-handling methods can be integrated. Pretrained word embeddings are another key component of most neural named entity classifiers. With the advent of more complex contextual word embeddings, an interesting trade-off between model size and performance arises. While these techniques have been shown to work well in high-resource settings, we want to study how they perform in low-resource scenarios. In this work, we perform named entity recognition for Hausa and Yor\`ub\'a, two languages that are widely spoken in several developing countries. We evaluate different embedding approaches and show that distant supervision can be successfully leveraged in a realistic low-resource scenario where it can more than double a classifier's performance.
Open AccessDistant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá
The lack of labeled training data has limited the development of natural language processing tools, such as named entity recognition, for many languages spoken in developing countries. Techniques such as distant and weak supervision can be used to create labeled data in a (semi-) automatic way. Additionally, to alleviate some of the negative effects of the errors in automatic annotation, noise-handling methods can be integrated. Pretrained word embeddings are another key component of most neural named entity classifiers. With the advent of more complex contextual word embeddings, an interesting trade-off between model size and performance arises. While these techniques have been shown to work well in high-resource settings, we want to study how they perform in low-resource scenarios. In this work, we perform named entity recognition for Hausa and Yor\`ub\'a, two languages that are widely spoken in several developing countries. We evaluate different embedding approaches and show that distant supervision can be successfully leveraged in a realistic low-resource scenario where it can more than double a classifier's performance.
- Open Access
Feature-Dependent Confusion Matrices for Low-Resource NER Labeling with Noisy Labels
In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but often noisy. Previous works have shown that significant improvements can be reached by injecting information about the confusion between clean and noisy labels in this additional training data into the classifier training. However, for noise estimation, these approaches either do not take the input features (in our case word embeddings) into account, or they need to learn the noise modeling from scratch which can be difficult in a low-resource setting. We propose to cluster the training data using the input features and then compute different confusion matrices for each cluster. To the best of our knowledge, our approach is the first to leverage feature-dependent noise modeling with pre-initialized confusion matrices. We evaluate on low-resource named entity recognition settings in several languages, showing that our methods improve upon other confusion-matrix based methods by up to 9%.
Open AccessFeature-Dependent Confusion Matrices for Low-Resource NER Labeling with Noisy Labels
In low-resource settings, the performance of supervised labeling models can be improved with automatically annotated or distantly supervised data, which is cheap to create but often noisy. Previous works have shown that significant improvements can be reached by injecting information about the confusion between clean and noisy labels in this additional training data into the classifier training. However, for noise estimation, these approaches either do not take the input features (in our case word embeddings) into account, or they need to learn the noise modeling from scratch which can be difficult in a low-resource setting. We propose to cluster the training data using the input features and then compute different confusion matrices for each cluster. To the best of our knowledge, our approach is the first to leverage feature-dependent noise modeling with pre-initialized confusion matrices. We evaluate on low-resource named entity recognition settings in several languages, showing that our methods improve upon other confusion-matrix based methods by up to 9%.
- Open Access
Using Multi-Sense Vector Embeddings for Reverse Dictionaries
Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for each sense of a word. However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word. In this work, we study the effect of multi-sense embeddings on the task of reverse dictionaries. We propose a technique to easily integrate them into an existing neural network architecture using an attention mechanism. Our experiments demonstrate that large improvements can be obtained when employing multi-sense embeddings both in the input sequence as well as for the target representation. An analysis of the sense distributions and of the learned attention is provided as well.
Open AccessUsing Multi-Sense Vector Embeddings for Reverse Dictionaries
Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for each sense of a word. However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word. In this work, we study the effect of multi-sense embeddings on the task of reverse dictionaries. We propose a technique to easily integrate them into an existing neural network architecture using an attention mechanism. Our experiments demonstrate that large improvements can be obtained when employing multi-sense embeddings both in the input sequence as well as for the target representation. An analysis of the sense distributions and of the learned attention is provided as well.
- Open Access
Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is less effective due to unreliable annotations created using self-labeling of unlabeled data. We propose to combine self-training with noise handling on the self-labeled data. Directly estimating noise on the combined clean training set and self-labeled data can lead to corruption of the clean data and hence, performs worse. Thus, we propose the Clean and Noisy Label Neural Network which trains on clean and noisy self-labeled data simultaneously by explicitly modelling clean and noisy labels separately. In our experiments on Chunking and NER, this approach performs more robustly than the baselines. Complementary to this explicit approach, noise can also be handled implicitly with the help of an auxiliary learning task. To such a complementary approach, our method is more beneficial than other baseline methods and together provides the best performance overall.
Open AccessHandling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling
In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is less effective due to unreliable annotations created using self-labeling of unlabeled data. We propose to combine self-training with noise handling on the self-labeled data. Directly estimating noise on the combined clean training set and self-labeled data can lead to corruption of the clean data and hence, performs worse. Thus, we propose the Clean and Noisy Label Neural Network which trains on clean and noisy self-labeled data simultaneously by explicitly modelling clean and noisy labels separately. In our experiments on Chunking and NER, this approach performs more robustly than the baselines. Complementary to this explicit approach, noise can also be handled implicitly with the help of an auxiliary learning task. To such a complementary approach, our method is more beneficial than other baseline methods and together provides the best performance overall.